% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Khler:892689,
      author       = {Köhler, Cristiano and Ulianych, Danylo and Gerkin, Richard
                      C. and Davison, Andrew P. and Grün, Sonja and Denker,
                      Michael},
      title        = {{C}apturing detailed provenance information in the analysis
                      of electrophysiology data},
      reportid     = {FZJ-2021-02267},
      year         = {2021},
      abstract     = {The analysis of electrophysiology data typically comprises
                      multiple steps. These often consist of several scripts
                      executed in a specific sequence that take different
                      parameter sets and use distinct data files. As the
                      researcher adjusts the individual analysis steps to
                      accommodate new hypotheses or additional data, the resulting
                      workflows may become increasingly complex, and undergo
                      frequent changes. Therefore, robust tools forming the
                      workflows are necessary to fully document the workflow and
                      improve the reproducibility of the results. Provenance
                      refers to the characterization of data manipulations and
                      corresponding parameters throughout the analysis [1]. It is
                      possible to use workflow management systems to orchestrate
                      the execution of the scripts and capture provenance
                      information at the level of the script (i.e., which script
                      file was executed, and in which environment?) and data file
                      (i.e., which input and output files were supplied to that
                      script). However, the resulting provenance track does not
                      automatically provide details about the actual analysis
                      carried out inside each script. Thus, analysis results can
                      only be understood by source code inspection or trust in the
                      correctness of any accompanying documentation. Here, we aim
                      to improve existing tools by implementing a data model that
                      captures detailed provenance information and by accurately
                      representing the analysis results in a systematic and
                      formalized manner. We focus on two open-source tools for the
                      analysis of electrophysiology data. The Neo
                      $(RRID:SCR_000634)$ framework provides an object model to
                      standardize neural activity data acquired from distinct
                      sources [2]. Elephant $(RRID:SCR_003833)$ is a Python
                      toolbox that provides several functions for the analysis of
                      electrophysiology data.3 We implemented prototypes of two
                      complementary solutions to extend the functionality of Neo
                      and Elephant to (i) automatically capture provenance
                      information at the function-execution level inside a Python
                      script, and to (ii) support the standardization of the
                      analysis results together with the storage of relevant
                      information describing their generation. The first solution
                      is a set of data analysis objects that standardize the
                      output of Elephant functions. They encapsulate all relevant
                      parameters used by the function to generate the output, such
                      that they can be easily re-used or shared. The second
                      solution maps function inputs, outputs, and parameters
                      throughout the execution of the Python analysis script, and
                      builds a representation of the relationships between the
                      different steps of the analysis within the script (i.e., the
                      provenance trace). The captured information can be used to
                      build a graph to visualize the steps followed in the script,
                      and that can be stored together with the results as
                      metadata. We compare the results obtained with or without
                      the use of the two solutions on the basis of a realistic
                      analysis scenario of electrophysiology data, showing the
                      potential benefits for reproducibility, interoperability,
                      discoverability, and re-use of analysis results. References:
                      [1] Ragan et al. (2016) IEEE Trans Visual Comput Graphics
                      22:31. [2] Garcia et al. (2014) Front Neuroinform 8:10. [3]
                      http://python-elephant.org.},
      month         = {Mar},
      date          = {2021-03-22},
      organization  = {14th Göttingen Meeting of the German
                       Neuroscience Society 2021, online
                       (Germany), 22 Mar 2021 - 30 Mar 2021},
      subtyp        = {Other},
      cin          = {INM-6 / INM-10 / IAS-6},
      cid          = {I:(DE-Juel1)INM-6-20090406 / I:(DE-Juel1)INM-10-20170113 /
                      I:(DE-Juel1)IAS-6-20130828},
      pnm          = {5235 - Digitization of Neuroscience and User-Community
                      Building (POF4-523) / 5231 - Neuroscientific Foundations
                      (POF4-523) / 571 - Connectivity and Activity (POF3-571) /
                      574 - Theory, modelling and simulation (POF3-574) / HDS LEE
                      - Helmholtz School for Data Science in Life, Earth and
                      Energy (HDS LEE) (HDS-LEE-20190612) / HBP SGA2 - Human Brain
                      Project Specific Grant Agreement 2 (785907) / HBP SGA3 -
                      Human Brain Project Specific Grant Agreement 3 (945539) /
                      HAF - Helmholtz Analytics Framework (ZT-I-0003)},
      pid          = {G:(DE-HGF)POF4-5235 / G:(DE-HGF)POF4-5231 /
                      G:(DE-HGF)POF3-571 / G:(DE-HGF)POF3-574 /
                      G:(DE-Juel1)HDS-LEE-20190612 / G:(EU-Grant)785907 /
                      G:(EU-Grant)945539 / G:(DE-HGF)ZT-I-0003},
      typ          = {PUB:(DE-HGF)24},
      url          = {https://juser.fz-juelich.de/record/892689},
}